© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 12560
    Prev
    Next
    INDEX
    Explanations

    K, !, ' puzzle

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron fires strongly on longer, content‐heavy or domain‐specific terms (uncommon technical or proper‐noun words) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lective
    0.68
     年度
    0.68
     Appeals
    0.66
     philosophie
    0.65
    ឌ
    0.65
     Architektur
    0.65
     Allemagne
    0.64
    ക്കുകയും
    0.64
    ბ
    0.64
     Ecole
    0.64
    POSITIVE LOGITS
    тися
    0.89
    śmy
    0.79
    ಸ್ತಕ
    0.79
     monopolist
    0.78
    это
    0.76
     hetero
    0.75
     trở
    0.72
    cF
    0.72
    yan
    0.72
    kan
    0.71
    Activations Density 0.106%

    No Known Activations